Upload tokenizer
Browse files- tokenizer.json +1 -0
- tokenizer_config.json +1 -0
tokenizer.json
CHANGED
|
@@ -66,6 +66,7 @@
|
|
| 66 |
"continuing_subword_prefix": null,
|
| 67 |
"end_of_word_suffix": null,
|
| 68 |
"fuse_unk": false,
|
|
|
|
| 69 |
"vocab": {
|
| 70 |
"<unk>": 0,
|
| 71 |
"<pad>": 1,
|
|
|
|
| 66 |
"continuing_subword_prefix": null,
|
| 67 |
"end_of_word_suffix": null,
|
| 68 |
"fuse_unk": false,
|
| 69 |
+
"byte_fallback": false,
|
| 70 |
"vocab": {
|
| 71 |
"<unk>": 0,
|
| 72 |
"<pad>": 1,
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"model_max_length": 1000000000000000019884624838656,
|
| 3 |
"pad_token": "<pad>",
|
| 4 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
| 1 |
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
"model_max_length": 1000000000000000019884624838656,
|
| 4 |
"pad_token": "<pad>",
|
| 5 |
"tokenizer_class": "PreTrainedTokenizerFast"
|